食品科学 ›› 2018, Vol. 39 ›› Issue (12): 319-325.doi: 10.7506/spkx1002-6630-201812049

• 安全检测 • 上一篇    

光谱预处理对太赫兹光谱预测猪肉K值的影响

齐亮1,2,赵茂程1,3,*,赵婕1,4,唐于维一1   

  1. (1.南京林业大学机械电子工程学院,江苏?南京 210037;2.南京师范大学分析测试中心,江苏?南京 210046;3.泰州学院,江苏?泰州 225300;4.南京工业职业技术学院航空工程学院,江苏?南京 210023)
  • 出版日期:2018-06-25 发布日期:2018-06-15
  • 基金资助:
    江苏省高校自然科学基金项目(15KJD550001);江苏省高校优势学科建设工程资助项目(PAPD); 2016年度省级战略性新兴产业发展专项资金项目;南京市2015年度科技发展计划项目(201505058); 国家自然科学基金面上项目(31570714)

Effects of Spectral Pretreatment on the Prediction of Pork K Value with Terahertz Spectroscopy

QI Liang1,2, ZHAO Maocheng1,3,*, ZHAO Jie1,4, TANG Yuweiyi1   

  1. (1. College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China;2. Center for Analysis and Testing, Nanjing Normal University, Nanjing 210046, China; 3. Taizhou University, Taizhou 225300, China;4. Aeronautical Engineering Department, Nanjing Institute of Industry Technology, Nanjing 210023, China)
  • Online:2018-06-25 Published:2018-06-15

摘要: 采用太赫兹(terahertz,THz)光谱分析技术无损检测猪肉的新鲜度K值,但水会强烈吸收THz波,从而严重影响THz波对肉的检测。考察预处理方法对削弱水的干扰、提升THz光谱检测猪肉K值的模型性能的影响。分别采用多元散射校正、标准正态变量变换、一阶微分、二阶微分4?种预处理方法对衰减全反射光谱进行预处理,基于反向传播人工神经网络回归算法建立猪肉K值的THz光谱预测模型,比较研究4?种预处理方法后的模型预测精度。研究表明:一阶微分预处理方法效果最好,能够消除光谱基线漂移,提高光谱质量。与原始光谱相比,模型的预测集相关系数(Rp)从0.34提高到0.75,预测集均方根误差从20.24%降低到14.36%。因此,选择合适的光谱预处理技术对提高模型预测精度非常重要,采用一阶微分预处理后的THz光谱数据建立反向传播人工神经网络模型能够无损检测猪肉的新鲜度K值。

关键词: 太赫兹光谱, 预处理, K值, 反向传播人工神经网络, 无损检测

Abstract: Adenosine triphosphate (ATP) and its degradation products, which are related to freshness K value, can absorb terahertz (THz) waves due to molecular rotation and vibration and overall vibration of molecular clusters. Thus, THz spectroscopy can be used to detect the K value of pork non-destructively. However, water can strongly absorb THz waves as well, which will affect the accuracy of the obtained results. In this study, different spectral preprocessing methods were compared for their efficiencies in weakening water interference and improving the performance of predictive models in the detection of pork K value by THz spectroscopy. Four spectral preprocessing methods, including multiple scatter correction (MSC), standard normal variate transformation (SNVT), first derivative (FD) and second derivative (SD), were employed to preprocess the original attenuated total reflectance (ATR) infrared spectra. Predictive models were established by back-propagation artificial neural network (BP-ANN) regression algorithm, and their precisions?were compared. The results showed that the FD pretreatment method was the most effective in eliminating baseline drift and improving the spectral quality. Compared with the predictive model without pretreatment, the correlation coefficient of prediction set (Rp) of the FD model was increased from 0.34 to 0.75, and the root mean square error of prediction set (RMSEP) was reduced from 20.24% to 14.36%. This study highlighted the importance of selecting the appropriate spectral pretreatment method to improve the predictive accuracy of models. The BP-ANN model based on FD pretreatment of THz spectra can be used to non-destructively detect pork freshness K value.

Key words: terahertz (THz) spectroscopy, pretreatment, K value, back propagation artificial neural network, non-destructive detection

中图分类号: